The Luonan Basin is a key region of early human settlement in Central China with more than 300 discovered Paleolithic sites. Artifact layer 1 of the Liuwan site was dated to approximately 0.6 million years (Ma) based ...The Luonan Basin is a key region of early human settlement in Central China with more than 300 discovered Paleolithic sites. Artifact layer 1 of the Liuwan site was dated to approximately 0.6 million years (Ma) based on correlation with the well-dated loess-paleosol sequence of the central Chinese Loess Plateau. This study reassessed the age of the Liuwan artifact layer via an absolute dating method, namely, <sup>26</sup>Al/<sup>10</sup>Be burial dating. We determined the burial age of artifact layer 1, which was most likely at least 0.60 ± 0.12 Ma (1ơ), using three simple burial ages. The new burial age confirmed the previous estimated age and provided a considerably accurate age range. Therefore, we suggest the use of the <sup>26</sup>Al/<sup>10</sup>Be burial dating method in thin loess-covered Paleolithic sites around the Qinling Mountain Range is helpful to understand the early human behavior.展开更多
建筑平面图外墙的自动识别在建筑设计和施工的过程中具有重要意义,它不仅能提高设计效率,还能辅助设计审核,降低图纸错误风险。同时,自动识别外墙等构件为三维模型的快速生成提供有效数据,推动建筑信息建模(Building Information Modeli...建筑平面图外墙的自动识别在建筑设计和施工的过程中具有重要意义,它不仅能提高设计效率,还能辅助设计审核,降低图纸错误风险。同时,自动识别外墙等构件为三维模型的快速生成提供有效数据,推动建筑信息建模(Building Information Modeling,BIM)技术的发展。目前自动识别建筑平面图外墙的方法主要是基于规则的方法,且其效果仍有一定的提升空间。针对上述问题,本文提出了一种基于Swin Transformer和LSTM的CycleGAN算法实现建筑平面图外墙的自动识别,以辅助建筑平面图的设计、建筑平面图设计的质量稽查、三维模型的快速生成等。该算法基于循环一致性生成对抗网络(CycleGAN)框架,嵌入Swin Transformer Block模块和长短期记忆(Long Short-Term Memory,LSTM)模块,增强模型特征提取能力和网络学习能力。实验结果表明,改进的CycleGAN算法实现了非成对训练样本条件下建筑平面图外墙的识别,在结构相似性指数和峰值信噪比的两个指标上分别提高了22.4%和4.223,且生成的建筑外墙图具有清晰度高、细节特征完整的特点。展开更多
基金National Natural Science Foundation of China,No.41572155,No.41690111The Global Change Program of the Ministry of Science and Technology of China,No.2016YFA0600503
文摘The Luonan Basin is a key region of early human settlement in Central China with more than 300 discovered Paleolithic sites. Artifact layer 1 of the Liuwan site was dated to approximately 0.6 million years (Ma) based on correlation with the well-dated loess-paleosol sequence of the central Chinese Loess Plateau. This study reassessed the age of the Liuwan artifact layer via an absolute dating method, namely, <sup>26</sup>Al/<sup>10</sup>Be burial dating. We determined the burial age of artifact layer 1, which was most likely at least 0.60 ± 0.12 Ma (1ơ), using three simple burial ages. The new burial age confirmed the previous estimated age and provided a considerably accurate age range. Therefore, we suggest the use of the <sup>26</sup>Al/<sup>10</sup>Be burial dating method in thin loess-covered Paleolithic sites around the Qinling Mountain Range is helpful to understand the early human behavior.
